INDEX

Explanations

patterns in control structures, particularly loops and range functions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Following certain symbols or numbers

np_acts-logits-general · gemini-2.0-flash

was improperly

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.68

MigrationBuilder

-0.65

řad

-0.56

 finder

-0.52

 חיצוניים

-0.52

ListTile

-0.51

 ویکی‌پدیا

-0.49

 būt

-0.49

busters

-0.49

 Spisak

-0.48

POSITIVE LOGITS

IsPostBack

0.57

ponses

0.49

IPE

0.49

(!__

0.47

CppMethod

0.47

ResumeLayout

0.45

unsigned

0.44

fitriones

0.44

lismo

0.42

adaptiveStyles

0.42

Activations Density 0.182%

patterns in control structures, particularly loops and range functions

Following certain symbols or numbers

was improperly

No Comments

No Known Activations